© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37954
    Prev
    Next
    INDEX
    Explanations

    all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Arbeit
    -0.81
    Při
    -0.76
    tilen
    -0.76
     boyunca
    -0.75
     specialist
    -0.75
    手的
    -0.74
    ILLER
    -0.74
    inFile
    -0.74
    orderId
    -0.73
     väga
    -0.73
    POSITIVE LOGITS
    all
    2.31
     all
    2.19
    alls
    1.91
    All
    1.91
     All
    1.86
    ALL
    1.66
     все
    1.48
     ALL
    1.47
     alls
    1.46
    Все
    1.36
    Activations Density 0.026%

    No Known Activations